refactor: rename clawdbot to moltbot with legacy compat
This commit is contained in:
Peter Steinberger
@@ -1,12 +1,12 @@
|
||||
---
|
||||
summary: "How Clawdbot memory works (workspace files + automatic memory flush)"
|
||||
summary: "How Moltbot memory works (workspace files + automatic memory flush)"
|
||||
read_when:
|
||||
- You want the memory file layout and workflow
|
||||
- You want to tune the automatic pre-compaction memory flush
|
||||
---
|
||||
# Memory
|
||||
|
||||
Clawdbot memory is **plain Markdown in the agent workspace**. The files are the
|
||||
Moltbot memory is **plain Markdown in the agent workspace**. The files are the
|
||||
source of truth; the model only "remembers" what gets written to disk.
|
||||
|
||||
Memory search tools are provided by the active memory plugin (default:
|
||||
@@ -36,7 +36,7 @@ These files live under the workspace (`agents.defaults.workspace`, default
|
||||
|
||||
## Automatic memory flush (pre-compaction ping)
|
||||
|
||||
When a session is **close to auto-compaction**, Clawdbot triggers a **silent,
|
||||
When a session is **close to auto-compaction**, Moltbot triggers a **silent,
|
||||
agentic turn** that reminds the model to write durable memory **before** the
|
||||
context is compacted. The default prompts explicitly say the model *may reply*,
|
||||
but usually `NO_REPLY` is the correct response so the user never sees this turn.
|
||||
@@ -75,13 +75,13 @@ For the full compaction lifecycle, see
|
||||
|
||||
## Vector memory search
|
||||
|
||||
Clawdbot can build a small vector index over `MEMORY.md` and `memory/*.md` so
|
||||
Moltbot can build a small vector index over `MEMORY.md` and `memory/*.md` so
|
||||
semantic queries can find related notes even when wording differs.
|
||||
|
||||
Defaults:
|
||||
- Enabled by default.
|
||||
- Watches memory files for changes (debounced).
|
||||
- Uses remote embeddings by default. If `memorySearch.provider` is not set, Clawdbot auto-selects:
|
||||
- Uses remote embeddings by default. If `memorySearch.provider` is not set, Moltbot auto-selects:
|
||||
1. `local` if a `memorySearch.local.modelPath` is configured and the file exists.
|
||||
2. `openai` if an OpenAI key can be resolved.
|
||||
3. `gemini` if a Gemini key can be resolved.
|
||||
@@ -89,7 +89,7 @@ Defaults:
|
||||
- Local mode uses node-llama-cpp and may require `pnpm approve-builds`.
|
||||
- Uses sqlite-vec (when available) to accelerate vector search inside SQLite.
|
||||
|
||||
Remote embeddings **require** an API key for the embedding provider. Clawdbot
|
||||
Remote embeddings **require** an API key for the embedding provider. Moltbot
|
||||
resolves keys from auth profiles, `models.providers.*.apiKey`, or environment
|
||||
variables. Codex OAuth only covers chat/completions and does **not** satisfy
|
||||
embeddings for memory search. For Gemini, use `GEMINI_API_KEY` or
|
||||
@@ -197,15 +197,15 @@ Local mode:
|
||||
- File type: Markdown only (`MEMORY.md`, `memory/**/*.md`).
|
||||
- Index storage: per-agent SQLite at `~/.clawdbot/memory/<agentId>.sqlite` (configurable via `agents.defaults.memorySearch.store.path`, supports `{agentId}` token).
|
||||
- Freshness: watcher on `MEMORY.md` + `memory/` marks the index dirty (debounce 1.5s). Sync is scheduled on session start, on search, or on an interval and runs asynchronously. Session transcripts use delta thresholds to trigger background sync.
|
||||
- Reindex triggers: the index stores the embedding **provider/model + endpoint fingerprint + chunking params**. If any of those change, Clawdbot automatically resets and reindexes the entire store.
|
||||
- Reindex triggers: the index stores the embedding **provider/model + endpoint fingerprint + chunking params**. If any of those change, Moltbot automatically resets and reindexes the entire store.
|
||||
|
||||
### Hybrid search (BM25 + vector)
|
||||
|
||||
When enabled, Clawdbot combines:
|
||||
When enabled, Moltbot combines:
|
||||
- **Vector similarity** (semantic match, wording can differ)
|
||||
- **BM25 keyword relevance** (exact tokens like IDs, env vars, code symbols)
|
||||
|
||||
If full-text search is unavailable on your platform, Clawdbot falls back to vector-only search.
|
||||
If full-text search is unavailable on your platform, Moltbot falls back to vector-only search.
|
||||
|
||||
#### Why hybrid?
|
||||
|
||||
@@ -266,7 +266,7 @@ agents: {
|
||||
|
||||
### Embedding cache
|
||||
|
||||
Clawdbot can cache **chunk embeddings** in SQLite so reindexing and frequent updates (especially session transcripts) don't re-embed unchanged text.
|
||||
Moltbot can cache **chunk embeddings** in SQLite so reindexing and frequent updates (especially session transcripts) don't re-embed unchanged text.
|
||||
|
||||
Config:
|
||||
|
||||
@@ -326,7 +326,7 @@ agents: {
|
||||
|
||||
### SQLite vector acceleration (sqlite-vec)
|
||||
|
||||
When the sqlite-vec extension is available, Clawdbot stores embeddings in a
|
||||
When the sqlite-vec extension is available, Moltbot stores embeddings in a
|
||||
SQLite virtual table (`vec0`) and performs vector distance queries in the
|
||||
database. This keeps search fast without loading every embedding into JS.
|
||||
|
||||
@@ -350,7 +350,7 @@ agents: {
|
||||
Notes:
|
||||
- `enabled` defaults to true; when disabled, search falls back to in-process
|
||||
cosine similarity over stored embeddings.
|
||||
- If the sqlite-vec extension is missing or fails to load, Clawdbot logs the
|
||||
- If the sqlite-vec extension is missing or fails to load, Moltbot logs the
|
||||
error and continues with the JS fallback (no vector table).
|
||||
- `extensionPath` overrides the bundled sqlite-vec path (useful for custom builds
|
||||
or non-standard install locations).
|
||||
|
||||
Reference in New Issue
Block a user